docs/zh-CN/skills/video-editing/SKILL.md
AI辅助的视频编辑工作流程,用于剪辑、构建和增强实拍素材。涵盖从原始拍摄到FFmpeg、Remotion、ElevenLabs、fal.ai,再到Descript或CapCut最终润色的完整流程。适用于用户想要编辑视频、剪辑素材、制作vlog或构建视频内容的情况。
npx skillsauth add affaan-m/everything-claude-code video-editingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
针对真实素材的AI辅助编辑。非根据提示生成。快速编辑现有视频。
当你不再要求AI创建整个视频,而是开始使用它来压缩、构建和增强真实素材时,AI视频编辑就变得有用了。价值不在于生成。价值在于压缩。
Screen Studio / 原始素材
→ Claude / Codex
→ FFmpeg
→ Remotion
→ ElevenLabs / fal.ai
→ Descript 或 CapCut
每个层级都有特定的工作。不要跳过层级。不要试图让一个工具完成所有事情。
收集源材料:
videodb 技能)输出:准备进行组织的原始文件。
使用Claude Code或Codex进行:
示例提示词:
"这是一份4小时录音的文字记录。找出最适合制作24分钟vlog的8个精彩片段。
为每个片段提供FFmpeg剪辑命令。"
此层级关乎结构,而非最终的创意品味。
FFmpeg处理枯燥但关键的工作:分割、修剪、连接和预处理。
ffmpeg -i raw.mp4 -ss 00:12:30 -to 00:15:45 -c copy segment_01.mp4
#!/bin/bash
# cuts.txt: start,end,label
while IFS=, read -r start end label; do
ffmpeg -i raw.mp4 -ss "$start" -to "$end" -c copy "segments/${label}.mp4"
done < cuts.txt
# Create file list
for f in segments/*.mp4; do echo "file '$f'"; done > concat.txt
ffmpeg -f concat -safe 0 -i concat.txt -c copy assembled.mp4
ffmpeg -i raw.mp4 -vf "scale=960:-2" -c:v libx264 -preset ultrafast -crf 28 proxy.mp4
ffmpeg -i raw.mp4 -vn -acodec pcm_s16le -ar 16000 audio.wav
ffmpeg -i segment.mp4 -af loudnorm=I=-16:TP=-1.5:LRA=11 -c:v copy normalized.mp4
Remotion将编辑问题转化为可组合的代码。用它来处理传统编辑器让工作变得痛苦的事情:
import { AbsoluteFill, Sequence, Video, useCurrentFrame } from "remotion";
export const VlogComposition: React.FC = () => {
const frame = useCurrentFrame();
return (
<AbsoluteFill>
{/* Main footage */}
<Sequence from={0} durationInFrames={300}>
<Video src="/segments/intro.mp4" />
</Sequence>
{/* Title overlay */}
<Sequence from={30} durationInFrames={90}>
<AbsoluteFill style={{
justifyContent: "center",
alignItems: "center",
}}>
<h1 style={{
fontSize: 72,
color: "white",
textShadow: "2px 2px 8px rgba(0,0,0,0.8)",
}}>
The AI Editing Stack
</h1>
</AbsoluteFill>
</Sequence>
{/* Next segment */}
<Sequence from={300} durationInFrames={450}>
<Video src="/segments/demo.mp4" />
</Sequence>
</AbsoluteFill>
);
};
npx remotion render src/index.ts VlogComposition output.mp4
有关详细模式和API参考,请参阅Remotion文档。
仅生成所需内容。不要生成整个视频。
import os
import requests
resp = requests.post(
f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}",
headers={
"xi-api-key": os.environ["ELEVENLABS_API_KEY"],
"Content-Type": "application/json"
},
json={
"text": "Your narration text here",
"model_id": "eleven_turbo_v2_5",
"voice_settings": {"stability": 0.5, "similarity_boost": 0.75}
}
)
with open("voiceover.mp3", "wb") as f:
f.write(resp.content)
使用 fal-ai-media 技能进行:
用于不存在的插入镜头、缩略图或B-roll素材:
generate(app_id: "fal-ai/nano-banana-pro", input_data: {
"prompt": "专业科技视频缩略图,深色背景,屏幕上显示代码",
"image_size": "landscape_16_9"
})
如果配置了VideoDB:
voiceover = coll.generate_voice(text="Narration here", voice="alloy")
music = coll.generate_music(prompt="lo-fi background for coding vlog", duration=120)
sfx = coll.generate_sound_effect(prompt="subtle whoosh transition")
最后一层由人工完成。使用传统编辑器进行:
品味体现在此。AI清理重复性工作。你做出最终决定。
不同平台需要不同的宽高比:
| 平台 | 宽高比 | 分辨率 | |----------|-------------|------------| | YouTube | 16:9 | 1920x1080 | | TikTok / Reels | 9:16 | 1080x1920 | | Instagram Feed | 1:1 | 1080x1080 | | X / Twitter | 16:9 或 1:1 | 1280x720 或 720x720 |
# 16:9 to 9:16 (center crop)
ffmpeg -i input.mp4 -vf "crop=ih*9/16:ih,scale=1080:1920" vertical.mp4
# 16:9 to 1:1 (center crop)
ffmpeg -i input.mp4 -vf "crop=ih:ih,scale=1080:1080" square.mp4
from videodb import ReframeMode
# Smart reframe (AI-guided subject tracking)
reframed = video.reframe(start=0, end=60, target="vertical", mode=ReframeMode.smart)
# Detect scene changes (threshold 0.3 = moderate sensitivity)
ffmpeg -i input.mp4 -vf "select='gt(scene,0.3)',showinfo" -vsync vfr -f null - 2>&1 | grep showinfo
# Find silent segments (useful for cutting dead air)
ffmpeg -i input.mp4 -af silencedetect=noise=-30dB:d=2 -f null - 2>&1 | grep silence
使用Claude分析转录稿 + 场景时间戳:
"根据这份带时间戳的转录稿和这些场景转换点,找出最适合社交媒体发布的5段30秒最吸引人的剪辑片段。"
| 工具 | 优势 | 劣势 | |------|----------|----------| | Claude / Codex | 组织、规划、代码生成 | 不是创意品味层 | | FFmpeg | 确定性剪辑、批量处理、格式转换 | 无可视化编辑UI | | Remotion | 可编程叠加层、可组合场景、可重复使用模板 | 对非开发者有学习曲线 | | Screen Studio | 即时获得精致的屏幕录制 | 仅限屏幕采集 | | ElevenLabs | 人声、旁白、音乐、音效 | 不是工作流程的核心 | | Descript / CapCut | 最终节奏调整、字幕、润色 | 手动操作,不可自动化 |
fal-ai-media — AI图像、视频和音频生成videodb — 服务器端视频处理、索引和流媒体content-engine — 平台原生内容分发development
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
development
Use when multiple consumers and providers must evolve an API or event schema without field drift, integration surprises, or one side silently redefining the interface.
tools
Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, and run explicitly gated node qualification through the separately installed canonical CLI. Use when a user asks to find H100/H200 capacity, request a fixed compute rate, check Itô compute status, or validate GPU nodes.
data-ai
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.